基于改进的ITD和模糊熵的滚动轴承故障诊断方法

中国机械工程 ›› 2012, Vol. 23 ›› Issue (19): 2372-2377.

基于改进的ITD和模糊熵的滚动轴承故障诊断方法

郑近德;程军圣;杨宇

湖南大学汽车车身先进设计制造国家重点实验室,长沙,410082

出版日期:2012-10-10 发布日期:2012-10-17
基金资助:
国家自然科学基金资助项目（51075131）；湖南省自然科学基金资助项目（11JJ2026）；湖南大学汽车车身先进设计制造国家重点实验室自主课题(61075002)；中央高校基本科研业务费专项基金资助项目(531107040301)
National Natural Science Foundation of China（No. 51075131）;

Hunan Provincial Natural Science Foundation of China（No. 11JJ2026）;
Fundamental Research Funds for the Central Universities( No. 531107040301 )

#br# A Rolling Bearing Fault Diagnosis Method Based on Improved ITD and Fuzzy Entropy

Zheng Jinde;Cheng Junsheng;Yang Yu

State key Laboratory of Advanced Design and Manufacture for Vehicle Body, Hunan University ,Changsha, 410082

Online:2012-10-10 Published:2012-10-17
Supported by:

National Natural Science Foundation of China（No. 51075131）;

Hunan Provincial Natural Science Foundation of China（No. 11JJ2026）;
Fundamental Research Funds for the Central Universities( No. 531107040301 )

摘要/Abstract

摘要：

提出了改进的本征时间尺度分解方法(improved intrinsic time-scale decomposition,IITD）。针对从滚动轴承的非线性和非平稳振动信号中提取故障特征难的问题,在IITD基础上,结合模糊熵的概念,提出了一种新的滚动轴承故障诊断方法。首先采用IITD方法对滚动轴承振动信号进行分解,再对得到的前几个有意义的合理旋转分量计算其模糊熵,并将熵值作为特征向量输入支持向量机分类器,从而实现滚动轴承故障类别的诊断。实验数据分析结果表明,所提出的方法可有效地实现滚动轴承故障类别的诊断。


关键词: 本征时间尺度分解, 模糊熵, 滚动轴承, 故障诊断

Abstract:

An improved ITD method was proposed. Meanwhile, for the difficulty that extracting fault features from the nonlinear and non-stationary vibration signals of rolling bearing, combined with the concept of fuzzy entropy, a new rolling bearing fault diagnosis method was put forward. Namely, decomposing the vibration signals of rolling bearing using the improved ITD method firstly, and calculating fuzzy entropies of the first few proper rotation components,then the entropy values as feature vectors were input to a SVM-based classifier to distinguish the rolling bearing fault types. By analysing the experimental data, the results show that the proposed method herein can diagnose the fault categories effectively.

Key words: intrinsic time-scale decomposition(ITD), fuzzy entropy, rolling bearing, fault diagnosis

中图分类号:

郑近德, 程军圣, 杨宇. 基于改进的ITD和模糊熵的滚动轴承故障诊断方法[J]. 中国机械工程, 2012, 23(19): 2372-2377.

ZHENG Jin-De, CHENG Jun-Ku, YANG Yu. #br# A Rolling Bearing Fault Diagnosis Method Based on Improved ITD and Fuzzy Entropy[J]. China Mechanical Engineering, 2012, 23(19): 2372-2377.

参考文献

[1]杨宇[1],于德介[1],程军圣[1].基于经验模态分解的滚动轴承故障诊断方法[J].中国机械工程,2004,15(10):908-911.
[2]罗洁思[1],于德介[1],彭富强[1].基于EMD的多尺度形态学解调方法及其在机械故障诊断中的应用[J].振动与冲击,2009(11).
[3]来凌红[1],吴虎胜[1],吕建新[1],刘凤[2],朱玉荣[1].基于EMD和样本熵的滚动轴承故障SVM识别[J].煤矿机械,2011,32(1):249-252.
[4]Pincus S M. Approximate Entropy as a Measure of System Complexity[J]. Proceedings of the National Academy of Sciences USA. , 1991,88:2297-2301.
[5]Richman J S, Moorman J R. Physiological Time-- series Analysis Using Approximate Entropy and Sample Entropy[J]. American Journal of Physiolo- gy- heart and Circulatory Physiology, 2000, 278: 2039-2049.
[6]刘慧[1],谢洪波[1,2],和卫星[1],王志中[3].基于模糊熵的脑电睡眠分期特征提取与分类[J].数据采集与处理,2010,25(4):484-489.
[7]Huang N E, Shen Z, Long S R, et al. The Empiri cal Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non- stationary Time Series Analysis[C]//Proceedings of the Royal Society of London,A, 1998, 454:903-995.
[8]Wu Z H, Huang N E. Ensemble Empirical Mode Decomposition: a Noise- assisted Data Analysis Method[J]. Advances in Adaptive Data Analysis, 2009,1(1) :1-41.
[9]戴桂平[1].基于EMD近似熵和DAGSVM的机械故障诊断[J].计量学报,2010(5):467-471.
[10]Frei M G,Osorio I. Intrinsic Time--scale Decom- position: Time-- frequency-- energy Analysis and Real--time Filtering of Non--stationary Signals [J]. Proceedings of the Royal Society A, 2007, 463 : 321-342.
[11]李岳[1],陶利民[1],温熙森[1].用于滚动轴承故障检测与分类的支持向量机方法[J].中国机械工程,2005,16(6):498-501.
[12]黄大吉,赵进平,苏纪兰.希尔伯特—黄变换的端点延拓[J].海洋学报,2003,25(1):1-11. 0
[13]邓拥军[1],王伟[2],钱成春[2],王忠[2],戴德君[2].EMD方法及Hilbert变换中边界问题的处理[J].科学通报,2001,46(3):257-263. 98
[14]程军圣[1],于德介[1],杨宇[1].基于支持矢量回归机的Hilbert-Huang变换端点效应问题的处理方法[J].机械工程学报,2006,42(4):23-31.
[15]Rilling G, Flandrin P, Goncalves P. On Empirical Mode Decomposition and Its Algorithms[C]//Pro- ceedings of IEEE--EURASIP Workshop on Non- linear Signal and Image Processing NSIP- 03. Graclo, 2003.
[16]陈伟婷.基于熵的表面肌电信号特征提取研究 [D].上海交通大学,2008: